# Training Articulatory Inversion Models for Interspeaker Consistency

arXiv: https://arxiv.org/abs/2505.20529 · HTML: https://mlsanity.com/paper/2505.20529/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 11 of 11)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus](https://mlsanity.com/paper/2305.18802/) (2023)
- [Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech](https://mlsanity.com/paper/2210.11723/) (2022)
- [Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?](https://mlsanity.com/paper/2204.12765/) (2022)
- [Coding Speech through Vocal Tract Kinematics](https://mlsanity.com/paper/2406.12998/) (2024)
- [RUSLAN: Russian Spoken Language Corpus for Speech Synthesis](https://mlsanity.com/paper/1906.11645/) (2019)

## Built on by (most cited first, 1 of 1)

- [Flexible and Interpretable Accent Distance Measurements](https://mlsanity.com/paper/2609.11458/) (2026)

## Abstract (arXiv)

Acoustic-to-Articulatory Inversion (AAI) attempts to model the inverse mapping from speech to articulation. Exact articulatory prediction from speech alone may be impossible, as speakers can choose different forms of articulation seemingly without reference to their vocal tract structure. However, once a speaker has selected an articulatory form, their productions vary minimally. Recent works in AAI have proposed adapting Self-Supervised Learning (SSL) models to single-speaker datasets, claiming that these single-speaker models provide a universal articulatory template. In this paper, we investigate whether SSL-adapted models trained on single and multi-speaker data produce articulatory targets which are consistent across speaker identities for English and Russian. We do this through the use of a novel evaluation method which extracts articulatory targets using minimal pair sets. We also present a training method which can improve interspeaker consistency using only speech data.